Classification of Prostate Cancer Patients and Healthy Individuals by Means of a Hybrid Algorithm Combing SVM and Evolutionary Algorithms


Por: Lasheras, J, Lasheras, F, Donquiles, C, Tardon, A, Vynals, G, Gomez, B, Palazuelos, C, Sala, D and Juez, F

Publicada: 1 ene 2018
Resumen:
This research presents a new hybrid algorithm able to select a set of features that makes it possible to classify healthy individuals and those affected by prostate cancer. In this research the feature selection is performed with the help of evolutionary algorithms. This kind of algorithms, have proven in previous researches their ability for obtaining solutions for optimization problems in very different fields. In this study, a hybrid algorithm based on evolutionary methods and support vector machine is developed for the selection of optimal feature subsets for the classification of data sets. The results of the algorithm using a reduced data set demonstrates the performance of the method when compared with non-hybrid methodologies.

Filiaciones:
Lasheras, J:
 Hosp Carmen & Severo Ochoa, Anesthesiol & Resuscitat Serv, Cangas De Narcea, Spain

Lasheras, F:
 Univ Oviedo, Dept Math, Oviedo, Spain

Donquiles, C:
 Ctr Invest Biomed Red Epidemiol & Salud Publ CIBE, Madrid, Spain

 Univ Oviedo, Univ Inst Oncol Asturias IUOPA, Oviedo, Spain

 Univ Leon, Biomed Inst IBIOMED, Res Grp Gene Environm Hlth Interact, Leon, Spain

Tardon, A:
 Ctr Invest Biomed Red Epidemiol & Salud Publ CIBE, Madrid, Spain

 Univ Oviedo, Univ Inst Oncol Asturias IUOPA, Oviedo, Spain

Vynals, G:
 Carlos III Inst Hlth, Consortium Biomed Res Epidemiol & Publ Hlth CIBER, Madrid, Spain

 Ctr Res Environm Epidemiol CREAL, ISGlobal, Barcelona, Spain

 UPF, Barcelona, Spain

 Hosp del Mar, Med Res Inst, IMIM, Barcelona, Spain

Gomez, B:
 Carlos III Inst Hlth, Consortium Biomed Res Epidemiol & Publ Hlth CIBER, Madrid, Spain

 Carlos III Inst Hlth, Natl Ctr Epidemiol, Canc Epidemiol Unit, Madrid, Spain

 IIS Puerta Hierro IDIPHIM, Oncol & Hematol Area, Canc Epidemiol Res Grp, Madrid, Spain

Palazuelos, C:
 Univ Cantabria, IDIVAL, Santander, Spain

:
 FISABIO Publ Hlth, Valencia Canc & Publ Hlth Area, Valencia, Spain

 Valencian Community, Gen Directorate Publ Hlth, Valencia, Spain

Juez, F:
 Univ Oviedo, Dept Mines Prospecting & Exploitat, Oviedo, Spain
ISSN: 03029743





Lecture Notes in Computer Science
Editorial
SPRINGER INTERNATIONAL PUBLISHING AG, GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND, Alemania
Tipo de documento: Proceedings Paper
Volumen: 10870 Número:
Páginas: 547-557
WOS Id: 000443487900046

MÉTRICAS